Skip to content
Evaluation sources

FrontierCode

Cognition / Coding · Quality, tests, and scope of changes on real repository tasks

Official evaluation
Across NexGateHub AI News Observing
Evidence budgetNot scored
Upstream data timeUnverified
Last successful syncCollection has not started

What it measures and how

Fixes v1.1 and official run conditions. Quality scores and test success together form one task-evidence item.

How this evidence is used

Under review: stable result exports and data-use terms are unconfirmed.

Evaluation limits & attribution

Under review: stable result exports and data-use terms are unconfirmed.

Data license: Leaderboard-data usage terms need confirmation.

Results are published by Cognition. Original scores and the NexGateHub consensus index use different scales and cannot be added directly.